Abstract
We propose the Detailed Outline Control (DOC) framework for improving long-range plot coherence when automatically generating several-thousand-word-long stories. DOC consists of two complementary components: a detailed outliner and a detailed controller. The detailed outliner creates a more detailed, hierarchically structured outline, shifting creative burden from the main drafting procedure to the planning stage. The detailed controller ensures the more detailed outline is still respected during generation by controlling story passages to align with outline details. In human evaluations of automatically generated stories, DOC substantially outperforms a strong Re3 baseline (Yang et al., 2022) on plot coherence (22.5% absolute gain), outline relevance (28.2%), and interestingness (20.7%). Humans also judged DOC to be much more controllable in an interactive generation setting.- Anthology ID:
- 2023.acl-long.190
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3378–3465
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.190
- DOI:
- 10.18653/v1/2023.acl-long.190
- Cite (ACL):
- Kevin Yang, Dan Klein, Nanyun Peng, and Yuandong Tian. 2023. DOC: Improving Long Story Coherence With Detailed Outline Control. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3378–3465, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- DOC: Improving Long Story Coherence With Detailed Outline Control (Yang et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2023.acl-long.190.pdf